ANS: Adaptive Network Scaling for Deep Rectifier Reinforcement Learning Models
This work provides a thorough study on how reward scaling can affect performance of deep reinforcement learning agents. In particular, we would like to answer the question that how does reward scaling affect non-saturating ReLU networks in RL? This question matters because ReLU is one of the most effective activation functions for deep learning models. We also propose an Adaptive Network Scaling framework to find a suitable scale of the rewards during learning for better performance. We conducted empirical studies to justify the solution.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Design of Adaptive Backstepping Control for Direct Power Control of Three-Phase PWM Rectifier)
In this paper, we focused on the design of an adaptive backstepping controller (adaptive-BSC) for direct power control (DPC) of a three-phase PWM rectifier. In the proposed system, it is desired to control both the outpu…
Delving into Rectifiers in Style-Based Image Translation
While modern image translation techniques can create photorealistic synthetic images, they have limited style controllability, thus could suffer from translation errors. In this work, we show that the activation function…
DiversityImage GenerationTranslationNeural Taylor Approximations: Convergence and Exploration in Rectifier Networks
Modern convolutional networks, incorporating rectifiers and max-pooling, are neither smooth nor convex; standard guarantees therefore do not apply. Nevertheless, methods from convex optimization such as gradient descent …
From Deep to Shallow: Transformations of Deep Rectifier Networks
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be…
Rectifier Neural Network with a Dual-Pathway Architecture for Image Denoising
Recently deep neural networks based on tanh activation function have shown their impressive power in image denoising. In this letter, we try to use rectifier function instead of tanh and propose a dual-pathway rectifier …
DenoisingImage Denoising